Uncertainty and Energy based Loss Guided Semi-Supervised Semantic Segmentation
This work addresses the challenge of reducing annotation costs in semantic segmentation, but it appears incremental as it builds on existing pseudolabel approaches.
The paper tackles the problem of semi-supervised semantic segmentation by using aleatoric uncertainty and energy-based modeling to improve pseudolabel supervision, resulting in performance improvements compared to state-of-the-art methods.
Semi-supervised (SS) semantic segmentation exploits both labeled and unlabeled images to overcome tedious and costly pixel-level annotation problems. Pseudolabel supervision is one of the core approaches of training networks with both pseudo labels and ground-truth labels. This work uses aleatoric or data uncertainty and energy based modeling in intersection-union pseudo supervised network.The aleatoric uncertainty is modeling the inherent noise variations of the data in a network with two predictive branches. The per-pixel variance parameter obtained from the network gives a quantitative idea about the data uncertainty. Moreover, energy-based loss realizes the potential of generative modeling on the downstream SS segmentation task. The aleatoric and energy loss are applied in conjunction with pseudo-intersection labels, pseudo-union labels, and ground-truth on the respective network branch. The comparative analysis with state-of-the-art methods has shown improvement in performance metrics.